{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T15:10:05Z","timestamp":1751382605860,"version":"3.41.0"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Since irregular 3D point clouds inherently lack connected relations, most approaches focus less on low-level spherical geometric features and high-level distant semantic feature dependencies and interactions, leading to inadequate feature representations for fine-grained point cloud understanding. To tackle the puzzle, we propose a novel and effective semantic-driven cross-space graph interaction network (CrossGIN) to explore and leverage local spatial features and range-aware semantic features across potential dual semantic spaces. Specifically, a local spatial aggregation is designed to capture position structures of spherical geometries by a spatial position module and enhance low-level spatial features using the semantic-aware module. Moreover, a graph interaction filter is proposed to dynamically aggregate the metric long-range semantic clues and better facilitate the adaptive feature interactions between 3D spatial and deep feature space. Finally, comprehensive experiments are conducted for 3D shape classification and object part segmentation tasks on several benchmark datasets such as ScanobjectNN, ModelNet40, and ShapeNetPart. The quantitative and qualitative results demonstrate that our method achieves competitive performance in comparison to recent approaches and verify the effectiveness of various modules.<\/jats:p>","DOI":"10.1145\/3735560","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T16:53:25Z","timestamp":1747155205000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-driven Cross-space Graph Interaction Network for Fine-grained 3D Point Cloud Understanding"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4195-3986","authenticated-orcid":false,"given":"Peng","family":"Ren","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2042-9237","authenticated-orcid":false,"given":"Yunfeng","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6069-6912","authenticated-orcid":false,"given":"Xiaoheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4452-1396","authenticated-orcid":false,"given":"Jinyuan","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"4179","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Anvekar Tejas","year":"2023","unstructured":"Tejas Anvekar and Dena Bazazian. 2023. GPr-Net: Geometric prototypical network for point cloud few-shot learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4179\u20134188."},{"issue":"2021","key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.neucom.2021.01.095","article-title":"GAPointNet: Graph attention based point neural network for exploiting local feature of point cloud","volume":"438","author":"Chen Can","year":"2021","unstructured":"Can Chen, Luca Zanotti Fragonara, and Antonios Tsourdos. 2021. GAPointNet: Graph attention based point neural network for exploiting local feature of point cloud. Neurocomputing 438, 2021 (2021), 122\u2013132.","journal-title":"Neurocomputing"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.1109\/ICME55011.2023.00341","volume-title":"Proceedings of the 2023 IEEE International Conference on Multimedia and Expo (ICME)","author":"Chen Chen","year":"2023","unstructured":"Chen Chen, Hui Yuan, Hao Liu, Junhui Hou, and Raouf Hamzaoui. 2023. CAS-Net: Cascade attention-based sampling neural network for point cloud simplification. In Proceedings of the 2023 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1991\u20131996."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072214"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00912"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_4"},{"key":"e_1_3_1_8_2","first-page":"2158","article-title":"LFT-Net: Local feature transformer network for point clouds analysis","volume":"24","author":"Gao Yongbin","year":"2022","unstructured":"Yongbin Gao, Xuebing Liu, Jun Li, Zhijun Fang, Xiaoyan Jiang, and Kazi Mohammed Saidul Huq. 2022. LFT-Net: Local feature transformer network for point clouds analysis. IEEE Transactions on Intelligent Transportation Systems 24 (2022), 2158\u20132168.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"e_1_3_1_12_2","first-page":"448","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the International Conference on Machine Learning. PMLR, 448\u2013456."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.99"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00959"},{"key":"e_1_3_1_16_2","first-page":"828","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Li Yangyan","year":"2018","unstructured":"Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. PointCNN: Convolution on X-transformed points. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, 828\u2013838."},{"issue":"8","key":"e_1_3_1_17_2","first-page":"4212","article-title":"Learning of 3D graph convolution networks for point cloud analysis","volume":"44","author":"Lin Zhi-Hao","year":"2021","unstructured":"Zhi-Hao Lin, Sheng-Yu Huang, and Yu-Chiang Frank Wang. 2021. Learning of 3D graph convolution networks for point cloud analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4212\u20134224.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"e_1_3_1_19_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv:1711.05101. Retrieved from https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_1_20_2","unstructured":"Dening Lu Qian Xie Mingqiang Wei Kyle Gao Linlin Xu and Jonathan Li. 2022. Transformers in 3D point clouds: A survey. arXiv:2205.07417. Retrieved from https:\/\/arxiv.org\/abs\/2205.07417"},{"key":"e_1_3_1_21_2","unstructured":"Xu Ma Can Qin Haoxuan You Haoxi Ran and Yun Fu. 2022. Rethinking network design and local geometry in point cloud: A simple residual MLP framework. arXiv:2202.07123. Retrieved from https:\/\/arxiv.org\/abs\/2202.07123"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_3_1_23_2","first-page":"3103","volume-title":"Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP)","author":"Seyed Saber Mohammadi","year":"2021","unstructured":"Seyed Saber Mohammadi, Yiming Wang, and Alessio Del Bue. 2021. Pointview-GCN: 3D shape classification with multi-view point clouds. In Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 3103\u20133107."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410439"},{"key":"e_1_3_1_25_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652\u2013660."},{"key":"e_1_3_1_26_2","first-page":"5105","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Ruizhongtai Qi Charles","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Proceedings of the 31st International Conference on Neural Information Processing Systems, 5105\u20135114."},{"key":"e_1_3_1_27_2","first-page":"23192","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Qian Guocheng","year":"2022","unstructured":"Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. PointNeXt: Revisiting PointNet++ with improved training and scaling strategies. In Proceedings of the 36th International Conference on Neural Information Processing Systems, 23192\u201323204."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074240"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_4"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01054"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs10040612"},{"issue":"4","key":"e_1_3_1_40_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073608","article-title":"O-CNN: Octree-based convolutional neural networks for 3D shape analysis","volume":"36","author":"Wang Peng-Shuai","year":"2017","unstructured":"Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. 2017. O-CNN: Octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics 36, 4 (2017), 1\u201311.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"issue":"8","key":"e_1_3_1_42_2","doi-asserted-by":"crossref","first-page":"4594","DOI":"10.1109\/TGRS.2018.2829625","article-title":"A deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification","volume":"56","author":"Wang Zhen","year":"2018","unstructured":"Zhen Wang, Liqiang Zhang, Liang Zhang, Roujing Li, Yibo Zheng, and Zidong Zhu. 2018. A deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification. IEEE Transactions on Geoscience and Remote Sensing 56, 8 (2018), 4594\u20134604.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_1_43_2","first-page":"1850","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei Xin","year":"2020","unstructured":"Xin Wei, Ruixuan Yu, and Jian Sun. 2020. View-GCN: View-based graph convolutional network for 3D shape analysis. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 1850\u20131859."},{"key":"e_1_3_1_44_2","first-page":"5333","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wu Chengzhi","year":"2023","unstructured":"Chengzhi Wu, Junwei Zheng, Julius Pfrommer, and J\u00fcrgen Beyerer. 2023. Attention-based point cloud edge sampling. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5333\u20135343."},{"key":"e_1_3_1_45_2","first-page":"1912","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1912\u20131920."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00570"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00344"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00760"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_3_1_52_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Zeng Wei","year":"2018","unstructured":"Wei Zeng and Theo Gevers. 2018. 3DContextNet: K-d tree guided hierarchical learning of point clouds using local and global contextual cues. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops."},{"key":"e_1_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Renrui Zhang Liuhui Wang Ziyu Guo Yali Wang Peng Gao Hongsheng Li and Jianbo Shi. 2023. Parameter is not all you need: Starting from non-parametric networks for 3D point cloud analysis. arXiv:2303.08134. Retrieved from https:\/\/arxiv.org\/abs\/2303.08134","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"e_1_3_1_54_2","first-page":"4965","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zhou Haoran","year":"2021","unstructured":"Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, and Tong Lu. 2021. Adaptive graph convolution for point cloud analysis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 4965\u20134974."},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538648"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T14:49:32Z","timestamp":1751381372000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735560"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3735560"],"URL":"https:\/\/doi.org\/10.1145\/3735560","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2024-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}